We live in a time of rapid technological change, where nearly every aspect of our lives now relies on devices that compute and connect. The resulting exponential increase in the use of cyber-physical systems has transformed industry, government, and commerce; what's more, the speed of innovation shows no signs of slowing down, particularly as the revolution in artificial intelligence (AI) stands to transform daily life even further through increasingly powerful tools for data analysis, prediction, security, and automation.1 Like past waves of extreme innovation, as this one crests, debate over ethical usage and privacy controls are likely to proliferate. So far, the intersection of AI and society has brought its own unique set of ethical challenges, some of which have been anticipated and discussed for many years, while others are just beginning to come to light. For example, academics and science fiction authors alike have long pondered the ethical implications of hyper-intelligent machines, but it's only recently that we've seen real-world problems start to surface, like social bias in automated decision-making tools, or the ethical choices made by self-driving cars.2, 5 During the past two decades, the security community has increasingly turned to AI and the power of machine learning (ML) to reap many technological benefits, but those advances have forced security practitioners to navigate a proportional number of risks and ethical dilemmas along the way. As the leader in the development of AI and ML for cybersecurity, BlackBerry Cylance is at the heart of the debate and is passionate about advancing the use of AI for good.

Transfer learning aims at improving the performance of target learners on target domains by transferring the knowledge contained in different but related source domains. In this way, the dependence on a large number of target domain data can be reduced for constructing target learners. Due to the wide application prospects, transfer learning has become a popular and promising area in machine learning. Although there are already some valuable and impressive surveys on transfer learning, these surveys introduce approaches in a relatively isolated way and lack the recent advances in transfer learning. As the rapid expansion of the transfer learning area, it is both necessary and challenging to comprehensively review the relevant studies. This survey attempts to connect and systematize the existing transfer learning researches, as well as to summarize and interpret the mechanisms and the strategies in a comprehensive way, which may help readers have a better understanding of the current research status and ideas. Different from previous surveys, this survey paper reviews over forty representative transfer learning approaches from the perspectives of data and model. The applications of transfer learning are also briefly introduced. In order to show the performance of different transfer learning models, twenty representative transfer learning models are used for experiments. The models are performed on three different datasets, i.e., Amazon Reviews, Reuters-21578, and Office-31. And the experimental results demonstrate the importance of selecting appropriate transfer learning models for different applications in practice.

Lateral phishing attacks – scams targeting users from compromised email accounts within an organization – are becoming an increasing concern in the U.S. Whereas in the past attackers would send phishing scams from email accounts external to an organization, recently there's been an explosion of email-borne scams in which an attackers compromise email accounts within organizations, and then uses those accounts to launch internal phishing emails to fellow employees – the kind of attacks known as lateral phishing. And when a phishing email comes from an internal account, the vast majority of email security systems can't stop it. Existing security systems largely detect cyber attacks that come from the outside, relying on signals like IP and domain reputation, which are ineffective when the email comes from an internal source. Lateral phishing attacks are also costly. FBI data shows that these cyberattacks caused more than $12 billion in losses between 2013-2018.

Generative adversarial networks (GANs) are deep neural networks that allow us to sample from an arbitrary probability distribution without explicitly estimating the distribution. There is a generator that takes a latent vector as input and transforms it into a valid sample from the distribution. There is also a discriminator that is trained to discriminate such fake samples from true samples of the distribution; at the same time, the generator is trained to generate fakes that the discriminator cannot tell apart from the true samples. Instead of learning a global generator, a recent approach involves training multiple generators each responsible from one part of the distribution. In this work, we review such approaches and propose the hierarchical mixture of generators, inspired from the hierarchical mixture of experts model, that learns a tree structure implementing a hierarchical clustering with soft splits in the decision nodes and local generators in the leaves. Since the generators are combined softly, the whole model is continuous and can be trained using gradient-based optimization, just like the original GAN model. Our experiments on five image data sets, namely, MNIST, FashionMNIST, UTZap50K, Oxford Flowers, and CelebA, show that our proposed model generates samples of high quality and diversity in terms of popular GAN evaluation metrics. The learned hierarchical structure also leads to knowledge extraction.

We study the problem, introduced by Qiao and Valiant, of learning from untrusted batches. Here, we assume $m$ users, all of whom have samples from some underlying distribution $p$ over $1, \ldots, n$. Each user sends a batch of $k$ i.i.d. samples from this distribution; however an $\epsilon$-fraction of users are untrustworthy and can send adversarially chosen responses. The goal is then to learn $p$ in total variation distance. When $k = 1$ this is the standard robust univariate density estimation setting and it is well-understood that $\Omega (\epsilon)$ error is unavoidable. Suprisingly, Qiao and Valiant gave an estimator which improves upon this rate when $k$ is large. Unfortunately, their algorithms run in time exponential in either $n$ or $k$. We first give a sequence of polynomial time algorithms whose estimation error approaches the information-theoretically optimal bound for this problem. Our approach is based on recent algorithms derived from the sum-of-squares hierarchy, in the context of high-dimensional robust estimation. We show that algorithms for learning from untrusted batches can also be cast in this framework, but by working with a more complicated set of test functions. It turns out this abstraction is quite powerful and can be generalized to incorporate additional problem specific constraints. Our second and main result is to show that this technology can be leveraged to build in prior knowledge about the shape of the distribution. Crucially, this allows us to reduce the sample complexity of learning from untrusted batches to polylogarithmic in $n$ for most natural classes of distributions, which is important in many applications. To do so, we demonstrate that these sum-of-squares algorithms for robust mean estimation can be made to handle complex combinatorial constraints (e.g. those arising from VC theory), which may be of independent technical interest.

PDFs, scans) into hierarchical structures is extensively demanded in the daily routines of many real-world applications, and is often a prerequisite step of many downstream NLP tasks. Earlier attempts focused on different but simpler tasks such as the detection of table or cell locations within documents; however, a holistic, principled approach to inferring the complete hierarchical structure in documents is missing. As a remedy, we developed "Doc-Parser": an end-to-end system for parsing the complete document structure - including all text elements, figures, tables, and table cell structures. To the best of our knowledge, Doc-Parser is the first system that derives the full hierarchical document compositions. Given the complexity of the task, annotating appropriate datasets is costly. Therefore, our second contribution is to provide a dataset for evaluating hierarchical document structure parsing. Our third contribution is to propose a scalable learning framework for settings where domain-specific data is scarce, which we address by a novel approach to weak supervision. Our computational experiments confirm the effectiveness of our proposed weak supervision: Compared to the baseline without weak supervision, it improves the mean average precision for detecting document entities by 37.1 % . When classifying hierarchical relations between entity pairs, it improves the F1 score by 27.6 % . 1 Introduction

The goal of coordinated multi-robot exploration tasks is to employ a team of autonomous robots to explore an unknown environment as quickly as possible. Compared with human-designed methods, which began with heuristic and rule-based approaches, learning-based methods enable individual robots to learn sophisticated and hard-to-design cooperation strategies through deep reinforcement learning technologies. However, in decentralized multi-robot exploration tasks, learning-based algorithms are still far from being universally applicable to the continuous space due to the difficulties associated with area calculation and reward function designing; moreover, existing learning-based methods encounter problems when attempting to balance the historical trajectory issue and target area conflict problem. Furthermore, the scalability of these methods to a large number of agents is poor because of the exponential explosion problem of state space. Accordingly, this paper proposes a novel approach - Multi-head Attention-based Multi-robot Exploration in Continuous Space (MAMECS) - aimed at reducing the state space and automatically learning the cooperation strategies required for decentralized multi-robot exploration tasks in continuous space. Computational geometry knowledge is applied to describe the environment in continuous space and to design an improved reward function to ensure a superior exploration rate. Moreover, the multi-head attention mechanism employed helps to solve the historical trajectory issue in the decentralized multi-robot exploration task, as well as to reduce the quadratic increase of action space.

More and more industries and organizations are leveraging artificial intelligence to delight customers and cut through the competition. However, development and deployment of deep learning models is time-consuming and costly – often prohibitively costly. That's when automated machine learning (AutoML) comes into play. AutoML solutions can significantly increase the efficiency of ML model development. Even more importantly, they lower the entry barriers for leveraging AI in business settings by allowing people without IT backgrounds to utilize the most advanced ML algorithms.

Machine Learning applied to financial services industry has the potential to improve outcomes for both businesses and consumers. And in the UK, firms are beginning to take advantage of this. A recent survey, called'Machine Learning in UK Financial Services', carried out by the Bank of England (BoE) and the Financial Conduct Authority (FCA) has found that two thirds of respondents report they already use it in some form. The median firm uses live ML applications in two business areas and this is expected to more than double within the next three years. The Bank of England (BoE) and Financial Conduct Authority (FCA) have a keen interest in the way that ML is being deployed by financial institutions.

The field of astronomy has arrived at a turning point in terms of size and complexity of both datasets and scientific collaboration. Commensurately, algorithms and statistical models have begun to adapt --- e.g., via the onset of artificial intelligence --- which itself presents new challenges and opportunities for growth. This white paper aims to offer guidance and ideas for how we can evolve our technical and collaborative frameworks to promote efficient algorithmic development and take advantage of opportunities for scientific discovery in the petabyte era. We discuss challenges for discovery in large and complex data sets; challenges and requirements for the next stage of development of statistical methodologies and algorithmic tool sets; how we might change our paradigms of collaboration and education; and the ethical implications of scientists' contributions to widely applicable algorithms and computational modeling. We start with six distinct recommendations that are supported by the commentary following them. This white paper is related to a larger corpus of effort that has taken place within and around the Petabytes to Science Workshops (https://petabytestoscience.github.io/).